© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 28160
    Prev
    Next
    INDEX
    Explanations

    mentions of doctors, specifically those labeled as "Dr." with varying levels of significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.12
    0.5%
    371
    +0.10
    0.4%
    385
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.05
    176
    +0.10
    0.04
    145
    +0.10
    0.04
    Negative Logits
     Mechdragon
    -0.70
    LOAD
    -0.70
     ashes
    -0.69
     Nato
    -0.63
     mail
    -0.62
     conformity
    -0.61
    HCR
    -0.61
     Typhoon
    -0.61
     summary
    -0.61
     goodbye
    -0.61
    POSITIVE LOGITS
    acon
    1.22
    agan
    1.21
    ago
    1.19
    udge
    1.18
    ifting
    1.17
    inks
    1.14
    astically
    1.09
    illing
    1.08
    unks
    1.07
    ilon
    1.07
    Activations Density 0.180%

    No Known Activations